plan_merge

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It states the operation is non-applying, returns a plan_id for a later apply step, and can be blocked by protected members. It does not mention plan expiration or persistence, but the key safety trait (no mutation yet) is explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences deliver the full essential contract without repeated schema content. Key constraints are front-loaded: previewability, memory count, non-application, plan_id routing, and protected-member behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a planning tool with no output schema, the description covers purpose, safety, next step, and a blocker. It is slightly short of a 5 because it omits the tool's relationship to merge_undo/merge_policy and any plan validity constraints, but none of these are required for a correct first call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are already fully documented in the schema. The description reinforces '2+ memories' and the diff output but does not need to add parameter-level details; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('Produce a previewable MERGE plan'), defines the resource (memories), and scopes it ('2+ memories') and the output (a diff of content/tags/provenance). It clearly distinguishes from apply_plan by stressing 'WITHOUT applying it', which disambiguates it from the apply sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: call this to preview a merge and get a plan_id for apply_plan, and it notes a blocking condition ('Protected members block the merge'). It does not explicitly enumerate when not to use related tools like plan_supersede or merge_candidates, so the guidance is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.